Launched this week
Yansu
AI that learns how you work and turns it into software
796 followers
AI that learns how you work and turns it into software
796 followers
Yanshu learns from the work you already do. It spots repeated tasks across files, messages, and workflows, then turns the best patterns into apps and automations. No process mapping or blank canvas—just the routines worth systemizing. Use it to automate recurring work, build lightweight internal tools, and speed up daily ops without writing code.
Congrats! scheduled automations based on daily patterns sound incredible. how long does Yansu typically observe before generating its first useful automation for a new user?
Yansu
@daniel_harris11 Usually a few times of repeat work will trigger it. Could be in the same day or a few days.
The other feature, hands-off is very nice. It can trigger almost instantly after install to have a quick "AHA" moment.
Congrats on the launch, Bo! this flips the script completely software acting proactively. how do you prevent Yansu from becoming overbearing or making incorrect assumptions about user intent without explicit input?
Yansu
@imogen_wallace Thank you! We do a few things that make it amazing experience for users.
1. We ask permissions before major decisions and share the reason why. This really helps user to understanding the intention behind it and the conversation from that also shape our future work. This really close the gap of incorrect assumptions.
2. Our "dreaming" feature each night reflects and distill from today's learning and knowledge and compare with before. So it will learn and explore your patterns. Focus on what it thinks you will like. And not focus on every single details.
Congrats on bringing bespoke software at scale to life! When Yansu observes screens to summarize intentions, what privacy safeguards exist to ensure sensitive data isn’t inadvertently used to build those apps?
Yansu
@alexander_gray3 We have many in the app to build the trust with user.
1. all information are stored locally
All understanding are locally
We automatically remove PII
User can add any disable application, Yansu will skip them completely
User has a quick disable action, for anything sensitive that is going on.
You mentioned summarize your intentions without explicitly telling AI. Are there edge cases where you still recommend users give explicit instructions?
@asher_luca Yes, definitely — passive generation still has boundaries.
Yansu is meant to pick up on repeated work patterns so users don’t have to keep prompting it. But explicit input still helps when you need something very specific, or when there’s an exception to a pattern it has already learned.
The goal isn’t to ask users for more instructions — it’s to let Yansu generate the right app quietly most of the time, and only bring users in when clarity, safety, or precision really matters.
Congrats this is genuinely futuristic! since software is built and refined continuously, how do you manage version control or rollbacks if a proactively built app breaks a critical workflow?
Yansu
@peyton_perez Great question
Under the hood, the system actually simulates all outcomes first before make the change permanent. What that means is each iteration will generate tons of test coverage before commit the new version. And we use the best practice of version control, in case when a breakage happens.
What happens when Yansu observes two competing intentions from the same user at different times of day—how does it resolve the conflict?
Yansu
@andrew_paul11 that's a challenge very hard to solve. We will use the previous learning to resolve it. And sometime, it does get wrong. but during the daily dreaming, it will correct, learn, and reflect
You said software becomes the proactive actor—does Yansu ever initiate a task without any prior observed signal, just based on predictive intuition?
Yansu
@benjamin_harris3 It proactively ask you, Can I do x/y/z, because of a/b/c. You are still in control